Plot correlation of light-dark samples to continuous light samples of cultivations performed in same Multi-Cultivator

Rows: 16 Columns: 52
── Column specification ───────────────────────────────────────────────────────────────────
Delimiter: "\t"
chr  (1): sgRNA
dbl (50): HL_5N2_t0_R1, HL_5N2_t0_R2, HL_5N2_t0_R3, HL_5N2_t0_R4, HL_5N2_t1_R1, HL_5N2_...
lgl  (1): Gene

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

1 Sample-sample correlation

df_counts <- tidyr::pivot_longer(count_matrix,
    cols = 2:ncol(count_matrix),
    names_to = "sample", values_to = "n_reads"
)

# sort
df_counts <- arrange(df_counts, sample)
#df_counts <- left_join(df_samplesheet, df_counts)

df_correlation <- df_counts %>%
    tidyr::pivot_wider(names_from = "sample", values_from = "n_reads") %>%
    dplyr::select(-c(1)) %>%
    cor()

plot_replicate_correlation <- df_correlation %>%
    dplyr::as_tibble() %>%
    dplyr::mutate(sample1 = colnames(.)) %>%
    tidyr::pivot_longer(
        cols = !sample1,
        names_to = "sample2", values_to = "cor_coef"
    ) %>%
    ggplot(aes(x = sample1, y = sample2, fill = cor_coef)) +
    geom_tile() +
    geom_text(color = grey(0.4), aes(label = round(cor_coef, 2))) +
    theme_light() +
    labs(title = "", x = "", y = "") +
    theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1)) +
    scale_fill_gradientn(
        colours = c("#E7298A", grey(0.9), "#66A61E"),
        limits = c(-1, 1)
    )

plot_replicate_correlation

ggsave("../plots/correlation/pdf/correlation_samples.pdf", plot=plot_replicate_correlation, width=12, height=12)
ggsave("../plots/correlation/png/correlation_samples.png", plot=plot_replicate_correlation, width=12, height=12)

# https://bioinformatics.stackexchange.com/questions/22502/manually-set-range-of-colour-scale-in-pheatmap-in-r

annotation_days = data.frame(row.names=unique(row.names(df_correlation)), generation=as.character(c(0, 0, 0,0, 1,1,1,1,2,2,2,2,3,3,3,3,4,4,4,4,5,5,5,5,6,6,6,6,7,7,7,7,0,0,0,1,1,1,2,2,2,3,3,3,4,4,4,5,5,5)), condition=c(rep("cont",32), rep("LD", 18)), replicate=as.character(c(rep(c(1,2,3,4),8), rep(c(5,6,7), 6)))) 

# https://stackoverflow.com/questions/41628450/r-pheatmap-change-annotation-colors-and-prevent-graphics-window-from-popping-up
# choose colors for replicate that make difference between the two conditions clearly obvious --> four colours that are similar for HC, three that are similar for LD, let replicate 3 of LD _pop_
# choose gradient of colors for generations
# e.g. Tol from https://davidmathlogic.com/colorblind/#%23D81B60-%231E88E5-%23FFC107-%23004D40
okabe <- c("#f0e442ff", "#e69f00ff", "#d55e00ff", "#cc79a7ff", "#009e73ff", "#56b4e9ff", "#0072b2ff", "#aaaaaaff")
tol <- c("#882255ff","#aa4499ff","#cc6677ff","#ddcc77ff","#88cceeff","#44aa99ff","#117733ff","#332288ff")
okabe_gen <- okabe
names(okabe_gen) <- unique(annotation_days$generation)
okabe_replic <- okabe[1:7]
names(okabe_replic) <- unique(annotation_days$replicate)
annotation_color_list <- list(condition=c("cont"=okabe[7], "LD"=okabe[2]), generation=okabe_gen, replicate=okabe_replic)

okabe <- c("#fff2ecff","#f0e442ff", "#f5a700ff", "#9a4400ff", "#cc79a7ff", "#56b4e9ff", "#0072b2ff", "#003450ff")
okabe_gen <- okabe
names(okabe_gen) <- unique(annotation_days$generation)
based_on_col <- c("#009affff","#007acbff","#005b98ff","#003d66ff","#ff9dd5ff","#cc84aeff","#9a5b83ff")
names(based_on_col) <- unique(annotation_days$replicate)
annotation_color_list <- list(condition=c("cont"="#005a96ff", "LD"="#c57ba5ff"), replicate=based_on_col, generation=okabe_gen)

color.divisions <- 100
#color <- makeColorRampPalette(c("navy", "white","white", "red"), cutoff.distance / max(distmat), color.divisions)


p <- pheatmap(df_correlation, display_numbers=TRUE, treeheight_col=0, cutree_rows = 3, cutree_cols = 3, annotation_row = annotation_days, annotation_colors = annotation_color_list)
p

ggsave("../plots/correlation/png/correlation_samples_clustering.png", plot=p, width=11.5, height=8)
ggsave("../plots/correlation/pdf/correlation_samples_clustering.pdf", plot=p, width=11.5, height=8)

p <- pheatmap(df_correlation, display_numbers=FALSE, treeheight_col=0, cutree_rows = 3, cutree_cols = 3, annotation_row = annotation_days, annotation_colors = annotation_color_list, breaks = seq(-1,1, length.out=(color.divisions + 1)))#, color = color)
p

ggsave("../plots/correlation/png/correlation_samples_clustering_woNumbers.png", plot=p, width=11.5, height=8)
ggsave("../plots/correlation/pdf/correlation_samples_clustering_woNumbers.pdf", plot=p, width=11.5, height=8)

Session Info